跳到正文
Jones Ray

ScholarPulse 日报 2026-07-16

2026-07-16 学术简报:2 篇。可重用代理技能的安全漏洞贯穿生命周期各阶段,需生命周期感知的安全分析。

今日速览

序号标题来源日期主题推荐等级
1Agent Skill Security: Threat Models, Attacks, Defenses, and EvaluationarXiv2026-07-15AI-Agent高
2NNStar: An end-to-end AI agent for nuclear matter and neutron star physicsarXiv2026-07-15AI-Agent高

重点论文与技术动态

1. Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

一句话结论

可重用代理技能的安全漏洞贯穿生命周期各阶段,需生命周期感知的安全分析。

本研究通过构建SkillSec-Eval框架,对327个真实技能进行实证评估,发现安全风险不仅存在于执行阶段,还广泛分布于仓库接纳、语义检索等环节,揭示了现有安全研究的局限性。

核心内容

方法与数据

价值判断

摘要 Reusable skills are becoming a fundamental building block of Large Language Model (LLM) agents, enabling capabilities to be packaged, shared, and reused across diverse applications. However, existing security research primarily focuses on prompt injection and runtime execution, leaving security risks throughout the broader skill lifecycle largely unexplored. In this paper, we present SkillSec-Eval, a lifecycle-aware framework for systematically evaluating the security of reusable agent skills. We first characterize the skill lifecycle and develop a threat taxonomy spanning repository admission, semantic retrieval, planner selection, execution, and skill evolution. We then instantiate this taxonomy in SkillSec-Eval and conduct a comprehensive empirical evaluation using a repository of 327 real-world skills. Our study demonstrates that vulnerabilities arise at multiple lifecycle stages beyond execution, highlighting the need for lifecycle-aware security analysis of reusable agent skills.

2. NNStar: An end-to-end AI agent for nuclear matter and neutron star physics

一句话结论

NNStar为核物质和中子星观测分析提供了一种新的AI驱动框架,显著提升模型约束效率。

核心内容

方法与数据

价值判断

摘要 Constraining the equation of state of dense matter requires confronting effective models with massive data that spans many orders of magnitude in scale, from sub-saturation nuclear matter properties to the masses, radii, and tidal deformabilities of neutron stars. Exploring the high-dimensional coupling space of such a model and fine tuning it against all of these constraints is a labor- and time-intensive task. We present \textsc{NNStar}, an end-to-end artificial-intelligence agent that automates this workflow. Rather than a bespoke application, \textsc{NNStar} is delivered as a portable \emph{skill} for an open large-language-model (LLM) agent platform -- a self-describing module that pairs worked usage conventions with symbolic and numerical physics engines that (i) build a relativistic mean-field model directly from a Lagrangian, (ii) solve the mean-field equations of motion and evaluate the saturation properties, (iii) construct the $β$-equilibrium equation of state, splice it to a crust, and integrate the Tolman--Oppenheimer--Volkoff equations, and (iv) score the resulting predictions through a Bayesian joint analysis against nuclear matter and astrophysical observations. The agent can read a model, fit its parameters, and report the full set of nuclear matter and neutron star observables without human intervention. \textsc{NNStar} therefore provides a new, AI-driven framework for analyzing nuclear matter and neutron-star observations.